Building effective knowledge graphs (KGs) for Retrieval-Augmented Generation (RAG) is pivotal for advancing question answering (QA) systems. However, its effectiveness is hindered by a fundamental disconnect: the knowledge graph (KG) construction process is decoupled from its downstream application, yielding suboptimal graph structures. To bridge this gap, we introduce AutoGraph-R1, the first framework to directly optimize KG construction for task performance using Reinforcement Learning (RL). AutoGraph-R1 trains an LLM constructor by framing graph generation as a policy learning problem, where the reward is derived from the graph's functional utility in a RAG pipeline. We design two novel, task-aware reward functions, one for graphs as knowledge carriers and another as knowledge indices. Across multiple QA benchmarks, AutoGraph-R1 consistently enables graph RAG methods to achieve significant performance gains over using task-agnostic baseline graphs. Our work shows it is possible to close the loop between construction and application, shifting the paradigm from building intrinsically ``good'' graphs to building demonstrably ``useful'' ones.

Simulating step-wise human behavior with Large Language Models (LLMs) has become an emerging research direction, enabling applications in various practical domains. While prior methods, including prompting, supervised fine-tuning (SFT), and reinforcement learning (RL), have shown promise in modeling step-wise behavior, they primarily learn a population-level policy without conditioning on a user's persona, yielding generic rather than personalized simulations. In this work, we pose a critical question: how can LLM agents better simulate personalized user behavior? We introduce Customer-R1, an RL-based method for personalized, step-wise user behavior simulation in online shopping environments. Our policy is conditioned on an explicit persona, and we optimize next-step rationale and action generation via action correctness reward signals. Experiments on the OPeRA dataset emonstrate that Customer-R1 not only significantly outperforms prompting and SFT-based baselines in next-action prediction tasks, but also better matches users' action distribution, indicating higher fidelity in personalized behavior simulation.

Multi-agent deployments of large language models (LLMs) are increasingly embedded in market, allocation, and governance workflows, yet covert coordination among agents can silently erode trust and social welfare. Existing audits are dominated by heuristics that lack theoretical guarantees, struggle to transfer across tasks, and seldom ship with the infrastructure needed for independent replication. We introduce Audit the Whisper, a conference-grade research artifact that spans theory, benchmark design, detection, and reproducibility. Our contributions are: (i) a channel-capacity analysis showing how interventions such as paraphrase, rate limiting, and role permutation impose quantifiable capacity penalties-operationalised via paired-run Kullback--Leibler diagnostics-that tighten mutual-information thresholds with finite-sample guarantees and full proofs; (ii) ColludeBench-v0, covering pricing, first-price auctions, peer review, and hosted Gemini/Groq APIs with configurable covert schemes, deterministic manifests, and reward instrumentation; and (iii) a calibrated auditing pipeline that fuses cross-run mutual information, permutation invariance, watermark variance, and fairness-aware acceptance bias, each tuned to a $10^{-3}$ false-positive budget and validated by 10k honest runs plus an e-value martingale. Across ColludeBench and external suites including Secret Collusion, CASE, Perfect Collusion Benchmark, and SentinelAgent, the union meta-test attains state-of-the-art power at fixed FPR while ablations surface price-of-auditing trade-offs and fairness-driven colluders invisible to MI alone. We release regeneration scripts, anonymized manifests, and documentation so that external auditors can reproduce every figure, satisfy double-blind requirements, and extend the framework with minimal effort.

Large language models (LLMs) are primarily accessed via commercial APIs, but this often requires users to expose their data to service providers. In this paper, we explore how users can stay in control of their data by using privacy profiles: simple natural language instructions that say what should and should not be revealed. We build a framework where a local model uses these instructions to rewrite queries, only hiding details deemed sensitive by the user, before sending them to an external model, thus balancing privacy with performance. To support this research, we introduce PEEP, a multilingual dataset of real user queries annotated to mark private content and paired with synthetic privacy profiles. Experiments with lightweight local LLMs show that, after fine-tuning, they not only achieve markedly better privacy preservation but also match or exceed the performance of much larger zero-shot models. At the same time, the system still faces challenges in fully adhering to user instructions, underscoring the need for models with a better understanding of user-defined privacy preferences.

Code generation is a core capability of large language models (LLMs), yet mainstream benchmarks (e.g., APPs and LiveCodeBench) contain questions with medium-level difficulty and pose no challenge to advanced LLMs. To better reflected the advanced reasoning and code generation ability, We introduce Humanity's Last Code Exam (HLCE), comprising 235 most challenging problems from the International Collegiate Programming Contest (ICPC World Finals) and the International Olympiad in Informatics (IOI) spanning 2010 - 2024. As part of HLCE, we design a harmonized online-offline sandbox that guarantees fully reproducible evaluation. Through our comprehensive evaluation, we observe that even the strongest reasoning LLMs: o4-mini(high) and Gemini-2.5 Pro, achieve pass@1 rates of only 15.9% and 11.4%, respectively. Meanwhile, we propose a novel "self-recognition" task to measure LLMs' awareness of their own capabilities. Results indicate that LLMs' self-recognition abilities are not proportionally correlated with their code generation performance. Finally, our empirical validation of test-time scaling laws reveals that current advanced LLMs have substantial room for improvement on complex programming tasks. We expect HLCE to become a milestone challenge for code generation and to catalyze advances in high-performance reasoning and human-AI collaborative programming. Our code and dataset are also public available(https://github.com/Humanity-s-Last-Code-Exam/HLCE).

Training robust retrieval and reranker models typically relies on large-scale retrieval datasets; for example, the BGE collection contains 1.6 million query-passage pairs sourced from various data sources. However, we find that certain datasets can negatively impact model effectiveness -- pruning 8 out of 15 datasets from the BGE collection, reduces the training set size by 2.35$\times$, surprisingly increases nDCG@10 on BEIR by 1.0 point. This motivates a deeper examination of training data quality, with a particular focus on "false negatives", where relevant passages are incorrectly labeled as irrelevant. We utilize LLMs as a simple, cost-effective approach to identify and relabel false negatives in training datasets. Experimental results show that relabeling false negatives as true positives improves both E5 (base) and Qwen2.5-7B retrieval models by 0.7$\unicode{x2013}$1.4 points on BEIR and by 1.7$\unicode{x2013}$1.8 points at nDCG@10 on zero-shot AIR-Bench evaluation. Similar gains are observed for rerankers fine-tuned on the relabeled data, such as Qwen2.5-3B on BEIR. The reliability of LLMs to identify false negatives is supported by human annotation results. Our training dataset and code are publicly available.

Recent claims of strong performance by Large Language Models (LLMs) on causal discovery are undermined by a key flaw: many evaluations rely on benchmarks likely included in pretraining corpora. Thus, apparent success suggests that LLM-only methods, which ignore observational data, outperform classical statistical approaches. We challenge this narrative by asking: Do LLMs truly reason about causal structure, and how can we measure it without memorization concerns? Can they be trusted for real-world scientific discovery? We argue that realizing LLMs' potential for causal analysis requires two shifts: (P.1) developing robust evaluation protocols based on recent scientific studies to guard against dataset leakage, and (P.2) designing hybrid methods that combine LLM-derived knowledge with data-driven statistics. To address P.1, we encourage evaluating discovery methods on novel, real-world scientific studies. We outline a practical recipe for extracting causal graphs from recent publications released after an LLM's training cutoff, ensuring relevance and preventing memorization while capturing both established and novel relations. Compared to benchmarks like BNLearn, where LLMs achieve near-perfect accuracy, they perform far worse on our curated graphs, underscoring the need for statistical grounding. Supporting P.2, we show that using LLM predictions as priors for the classical PC algorithm significantly improves accuracy over both LLM-only and purely statistical methods. We call on the community to adopt science-grounded, leakage-resistant benchmarks and invest in hybrid causal discovery methods suited to real-world inquiry.

The success of deep neural networks in tasks such as image recognition, natural language processing, and reinforcement learning has come at the cost of escalating computational and memory requirements. Modern models, often comprised of billions of parameters, demand significant resources for training and inference, rendering them impractical for deployment on resource-constrained devices like mobile phones, embedded systems, or IoT devices. To address this challenge, weight quantization--reducing the precision of neural network weights--has emerged as a promising technique to lower memory footprint and accelerate inference. In particular, one-bit quantization, which restricts weights to{+1, 1}, offers extreme compression (e.g., 32 memory reduction for 32-bit floats) and enables efficient hardware implementations using bitwise operations. Various works have explored the possibility of network quantization in the recent years. In particular, for Large Language Models (LLMs), some post-training have been able to reduce the model size via fine-tuning. Examples of such approach include GPTQ Frantar et al. (2022) which can quantize a 175 billion GPT model to 4 bits and QuIP which Chee et al. (2023) compresses Llama 2 70B to 2 and 3 bits. Furthermore, quantization-aware training approaches, such as Bitnet Wang et al. (2023), Bitnet 1.58b Ma et al. (2024), have been able to achieve one-bit language models with comparable performance to the models from the same weight class. For a recent survey on efficient LLMs we refer to Xu et al. (2024).

Membership Inference Attacks (MIAs) pose a critical privacy threat by enabling adversaries to determine whether a specific sample was included in a model's training dataset. Despite extensive research on MIAs, systematic comparisons between generative and discriminative classifiers remain limited. This work addresses this gap by first providing theoretical motivation for why generative classifiers exhibit heightened susceptibility to MIAs, then validating these insights through comprehensive empirical evaluation. Our study encompasses discriminative, generative, and pseudo-generative text classifiers across varying training data volumes, evaluated on nine benchmark datasets. Employing a diverse array of MIA strategies, we consistently demonstrate that fully generative classifiers which explicitly model the joint likelihood $P(X,Y)$ are most vulnerable to membership leakage. Furthermore, we observe that the canonical inference approach commonly used in generative classifiers significantly amplifies this privacy risk. These findings reveal a fundamental utility-privacy trade-off inherent in classifier design, underscoring the critical need for caution when deploying generative classifiers in privacy-sensitive applications. Our results motivate future research directions in developing privacy-preserving generative classifiers that can maintain utility while mitigating membership inference vulnerabilities.

T he prompts read like tiny, abstract poems. The scenes come to life before my eyes in the form of AI-generated video. The videos pop up instantly--before my brain has had time to picture the prompts using my own imagination, as if the act of dreaming has been rendered obsolete, inefficient. I am experiencing Vibes, a new social network nested within the Meta AI app--except it's devoid of any actual people. This is a place where users can create an account and ask the company's large language model to illustrate their ideas. The resulting videos are then presented, seemingly at random, to others in a TikTok-style feed.